Research map / Image generation / Super-resolution
ATGV-Net: Accurate Depth Super-Resolution
Gernot Riegler, Matthias Rüther, Horst Bischof
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the variational ATGV model on top of the CNN without joint training (ablation) | ATGV-Net · Middlebury noisy x4, Art | RMSE: 3.55 -> 3.40 | Improved |
| add the variational ATGV model on top of the CNN without joint training (ablation) | ATGV-Net · Middlebury noisy x4, Books | RMSE: 2.41 -> 2.24 | Improved |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury noisy x4, Art | RMSE: 3.40 -> 2.98 | Improved |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury noisy x4, Books | RMSE: 2.24 -> 1.72 | Improved |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury noisy x4, Moebius | RMSE: 2.51 -> 1.95 | Improved |
| add the variational ATGV model on top of the CNN without joint training (ablation) | ATGV-Net · Middlebury clean x2, Cones | RMSE: 1.0275 -> 1.0145 | Improved |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury clean x4, Venus | RMSE: 0.4124 -> 0.3764 | Improved |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury clean x2, Tsukuba | RMSE: 2.3197 -> 2.3846 | Hurt |
| train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation) | ATGV-Net · Middlebury clean x4, Tsukuba | RMSE: 6.4223 -> 6.6327 | Hurt |
| add the variational ATGV model on top of the CNN without joint training (ablation) | ATGV-Net · Middlebury clean x2, Teddy | RMSE: 0.8201 -> 0.8374 | Hurt |
Closest papers by meaning
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.89)
- Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution (CVPR 2020 · similarity 0.88)
- SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution (AAAI 2024 · similarity 0.87)
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution (CVPR 2025 · similarity 0.86)
- Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution (CVPR 2025 · similarity 0.86)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
